DAGroup-PKU / MHLAView external linksLinks
MHLA: Restoring Expressivity of Linear Attention via Token-Level Multi-Head (ICLR 2026)
☆118Feb 6, 2026Updated last week
Alternatives and similar repositories for MHLA
Users that are interested in MHLA are comparing it to the libraries listed below
Sorting:
- FocusUI: Efficient UI Grounding via Position-Preserving Visual Token Selection☆24Updated this week
- ☆25Feb 6, 2026Updated last week
- [ICLR 2025] This repo is the official implementation of "The Labyrinth of Links: Navigating the Associative Maze of Multi-modal LLMs".☆13Jan 25, 2025Updated last year
- Medical SAM3: A Foundation Model for Universal Prompt-Driven Medical Image Segmentation☆88Jan 20, 2026Updated 3 weeks ago
- [ICLR 2026] Light-X: Generative 4D Video Rendering with Camera and Illumination Control☆166Dec 11, 2025Updated 2 months ago
- A specialized motion processing pipeline that converts GVHMR's SMPL outputs (.pt) into retargeted PBHC-compatible motions (.pkl), featuri…☆26Aug 19, 2025Updated 5 months ago
- ☆13Jul 10, 2024Updated last year
- ☆17May 21, 2025Updated 8 months ago
- ☆11Aug 13, 2024Updated last year
- daVinci-Agency: Unlocking Long-Horizon Agency Data-Efficiently☆32Feb 4, 2026Updated last week
- Official Implementation of the Paper:Motion-example-controlled Co-speech Gesture Generation Leveraging Large Language Models (Siggraph 20…☆22Dec 18, 2025Updated last month
- Aligning Agentic World Models via Knowledgeable Experience Learning☆30Jan 25, 2026Updated 3 weeks ago
- Official Repository for paper "HERMES: KV Cache as Hierarchical Memory for Efficient Streaming Video Understanding"☆58Jan 23, 2026Updated 3 weeks ago
- Towards Pixel-Level VLM Perception via Simple Points Prediction☆87Feb 9, 2026Updated last week
- X-Coder: Advancing Competitive Programming with Fully Synthetic Tasks, Solutions, and Tests☆78Feb 7, 2026Updated last week
- Orienting Latent Actions for Video World Modeling☆48Updated this week
- ☆16Mar 25, 2024Updated last year
- A unified robotic manipulation learning framework☆21Sep 4, 2025Updated 5 months ago
- KMM: Key Frame Mask Mamba for Extended Motion Generation☆19Sep 22, 2025Updated 4 months ago
- [CVPR2025] Is Your World Simulator a Good Story Presenter? A Consecutive Events-Based Benchmark for Future Long Video Generation☆18May 2, 2025Updated 9 months ago
- Official Implementation of "ToolSafe: Enhancing Tool Invocation Safety of LLM-based Agents via Proactive Step-level Guardrail and Feedbac…☆35Jan 23, 2026Updated 3 weeks ago
- 📷 Camera-controlled text-to-video generation, now with intrinsics, distortion and orientation control!☆116Feb 5, 2026Updated last week
- [ICLR 26] Part-X-MLLM: Part-aware 3D Multimodal Large Language Model☆110Jan 26, 2026Updated 3 weeks ago
- TBD☆39Feb 3, 2026Updated last week
- Official Implementation for *PaCo-RL: Advancing Reinforcement Learning for Consistent Image Generation with Pairwise Reward Modeling*☆31Dec 13, 2025Updated 2 months ago
- Reflect-DiT: Inference-Time Scaling for Text-to-Image Diffusion Transformers via In-Context Reflection☆55Aug 16, 2025Updated 6 months ago
- A Unified Visual Generator with Interleaved OmniModal Context☆180Updated this week
- The code of "HSR-KAN: Hyperspectral Image Super-Resolution based on Kolmogorov-Arnold Networks"☆24Sep 15, 2024Updated last year
- [ICME 2025] DiffusionTalker: Efficient and Compact Speech-Driven 3D Talking Head via Personalizer-Guided Distillation☆24Mar 25, 2025Updated 10 months ago
- Residual Context Diffusion (RCD): Repurposing discarded signals as structured priors for high-performance reasoning in dLLMs.☆52Updated this week
- the code of GRFormer: Grouped Residual Self-Attention for Lightweight Single Image Super-Resolution☆26May 16, 2024Updated last year
- ☆55Jan 30, 2026Updated 2 weeks ago
- [NeurIPS25] Official Implementation (Pytorch) of "DeepVideo-R1"☆31Nov 15, 2025Updated 3 months ago
- DiffThinker: Towards Generative Multimodal Reasoning with Diffusion Models☆169Jan 4, 2026Updated last month
- Dr. MAS is an end-to-end RL training framework for multi-agent LLM systems, supporting the co-training of multiple (heterogeneous) LLMs.☆60Updated this week
- ☆61Updated this week
- ReMoMask: Retrieval-Augmented Masked Motion Generation☆39Aug 29, 2025Updated 5 months ago
- ☆26Jun 22, 2024Updated last year
- Self-reimplemented version of 4D-LRM.☆65May 30, 2025Updated 8 months ago